Wind Power Prediction Research Articles

Study of Wind Power Prediction in ELM Based on Improved SSA

This paper proposes a short‐term wind power prediction model based on the improved Sparrow Search Algorithm (SSA) and Extreme Learning Machine(ELM) for anomalous wind power information from wind farms. The objective is to enhance the accuracy of short‐term wind power prediction. The model employs the extraction of features utilizing raw wind power history data from wind farms, in conjunction with the application of Variable Importance in Projection indices in Partial Least Squares (PLS‐VIP). As the ELM network model is susceptible to the influence of randomly generated input weights and thresholds at the outset of training, a solution is proposed whereby the input weights and thresholds of the ELM are optimized using SSA. The optimal weights and thresholds identified by SSA are then applied to the ELM model, thus forming the SSA‐ELM model. To address the limitations of traditional SSA, namely its susceptibility to local optimal solutions and poor global search ability, an improved SSA‐ELM algorithm is proposed. The improved SSA‐ELM algorithm introduces chaotic sequences and an exchange learning strategy to the original SSA. The rationale behind incorporating chaotic sequences is to enhance the quality of the initial solution, ensuring a more uniform distribution of sparrow positions and, consequently, a more diverse sparrow population. This, in turn, enables the algorithm to achieve a more effective global search capability through the utilization of the exchange learning strategy. Subsequently, all the data are fed into the SSA‐ELM model for prediction purposes. The simulation results demonstrate that the model exhibits enhanced prediction accuracy and improved practical applicability in wind power prediction. © 2025 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC.

A deep learning based short-term wind power prediction model with Fourier self-attention mechanism

A deep learning based short-term wind power prediction model with Fourier self-attention mechanism

Research on Low-Voltage Ride-Through and Intelligent Optimization Control of Wind Turbines Based on Hybrid Power Prediction Models

This paper proposes a dual-loop back-to-back converter coordination control scheme with a DC-side voltage as the primary control target, along with a CROW unloading control strategy for low voltage ride-through (LVRT) capability enhancement. The feasibility and effectiveness of the proposed system topology and control strategy are verified through MATLAB/Simulink simulations. Furthermore, a hybrid short-term wind power prediction model based on data-driven and deep learning techniques (CEEMDAN-CNN-Transformer-XGBoost) is introduced in the wind turbine control system. The coordination control strategy seamlessly integrates wind power prediction, pitch angle adjustment, and the control system, embodying a predictive-driven intelligent optimization control approach. This method significantly improves prediction accuracy and stability, theoretically reduces unnecessary pitch angle adjustments, lowers mechanical stress, and enhances system adaptability in complex operating conditions. The research findings provide a valuable theoretical foundation and technical reference for the intelligent and efficient operation of wind power generation systems.

Data Decomposition Modeling Based on Improved Dung Beetle Optimization Algorithm for Wind Power Prediction

Accurate wind power forecasting is essential for maintaining the stability of a power system and enhancing scheduling efficiency in the power sector. To enhance prediction accuracy, this paper presents a hybrid wind power prediction model that integrates the improved complementary ensemble empirical mode decomposition (ICEEMDAN), the RIME optimization algorithm (RIME), sample entropy (SE), the improved dung beetle optimization (IDBO) algorithm, the bidirectional long short-term memory (BiLSTM) network, and multi-head attention (MHA). In this model, RIME is utilized to improve the parameters of ICEEMDAN, reducing data decomposition complexity and effectively capturing the original data information. The IDBO algorithm is then utilized to improve the hyperparameters of the MHA-BiLSTM model. The proposed RIME-ICEEMDAN-IDBO-MHA-BiLSTM model is contrasted with ten others in ablation experiments to validate its performance. The experimental findings prove that the proposed model achieves MAPE values of 5.2%, 6.3%, 8.3%, and 5.8% across four datasets, confirming its superior predictive performance and higher accuracy.

MIVNDN: Ultra-Short-Term Wind Power Prediction Method with MSDBO-ICEEMDAN-VMD-Nons-DCTransformer Net

Wind speed, wind direction, humidity, temperature, altitude, and other factors affect wind power generation, and the uncertainty and instability of the above factors bring challenges to the regulation and control of wind power generation, which requires flexible management and scheduling strategies. Therefore, it is crucial to improve the accuracy of ultra-short-term wind power prediction. To solve this problem, this paper proposes an ultra-short-term wind power prediction method with MIVNDN. Firstly, the Spearman’s and Kendall’s correlation coefficients are integrated to select the appropriate features. Secondly, the multi-strategy dung beetle optimization algorithm (MSDBO) is used to optimize the parameter combinations in the improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) method, and the optimized decomposition method is used to decompose the historical wind power sequence to obtain a series of intrinsic modal function (IMF) components with different frequency ranges. Then, the high-frequency band IMF components and low-frequency band IMF components are reconstructed using the t-mean test and sample entropy, and the reconstructed high-frequency IMF component is decomposed quadratically using the variational modal decomposition (VMD) to obtain a new set of IMF components. Finally, the Nons-Transformer model is improved by adding dilated causal convolution to its encoder, and the new set of IMF components, as well as the unreconstructed mid-frequency band IMF components and the reconstructed low-frequency IMF, component are used as inputs to the model to obtain the prediction results and perform error analysis. The experimental results show that our proposed model outperforms other single and combined models.

A comprehensive evaluation of machine learning and deep learning algorithms for wind speed and power prediction

Accurate wind speed and power predictions are crucial for renewable wind energy applications. This study compares and evaluates twelve machine learning (ML) and deep learning (DL) algorithms, including single and ensemble models across various time scales from 10 min to a day and a half ahead with a particular focus on ensemble prediction algorithms. Moreover, the study proposes a wind speed and power prediction system where the outcome of the wind speed prediction (WSP) model serves as input for the wind power prediction (WPP) model. Several evaluation metrics, such as mean absolute percentage error (MAPE) and mean square error (MSE) were calculated to benchmark different model accuracies. For WSP, the extremely randomized trees, decision tree, and bagging ensemble algorithms demonstrated high accuracy across different time scales where the MAPE ranged from 3.4% to 9.2%, the MSE ranged from 0.17 to 1.15, and the adjusted coefficient of determination ranged from 94% to 99%. For WPP, bagging ensemble algorithms and extremely randomized trees were also effective for predicting different time scales where the MAPE ranged from 4.12% to 11.7% and the MSE ranged from 10945 to 2.4. Ensemble ML algorithms provide better and more accurate results than single ML algorithms. The extreme gradient boosting model showed relatively small computational time and memory according to computational cost. Moreover, this study conducted a sensitivity analysis where air pressure, wind vane, and humidity were the key predictors for WSP and WPP.

A Transferable Federated Learning Approach for Wind Power Prediction Based on Active Privacy Clustering and Knowledge Merge

As wind power continues to develop, advancing wind power prediction becomes more and more crucial. This study focuses on advancing wind power prediction by addressing data privacy and enhancing model applicability at multi-spatial scales, from individual turbines to entire farms. Traditional methods are typically confined to a single scale, lacking flexibility in application, requiring extensive data from farms, which potentially compromises energy data privacy. To tackle these challenges, we introduce an innovative Divide-Merge Federated Learning with Active Private Clustering (D-M APCFed) approach. This approach strategically employs federated learning to train models within privacy-preserving boundary, overcoming the adverse effects of wind power data heterogeneity through a novel APC method and knowledge merge technique. The primary innovation of this study is a scalable and accurate wind power prediction model that operates effectively at multi-spatial scales while safeguarding energy data privacy. In case study of two spatial scales, the D-M APCFed approach achieves an average prediction accuracy of 87.11% in the twelve federated farms and 81.69% in the twenty federated turbines. This approach enables a more generalized model through the secure use of data from diverse sources at multi-spatial scales, enhancing prediction accuracy and ensuring the confidentiality of sensitive information.

A hybrid wind power prediction model based on seasonal feature decomposition and enhanced feature extraction

Efficient and accurate wind power prediction is crucial for enhancing the reliability and safety of power system. The data-driven forecasting methods are regarded as an effective solution. However, the inherent randomness and nonlinearity of wind power systems, along with the abundance of redundant information in measurement data, present challenges to forecasting methods. The integration of precise and efficient techniques for data feature decomposition and extraction is essential in conjunction with advanced data-driven forecasting models. Focus on the seasonal variation characteristics of wind energy, a hybrid wind power prediction model based on seasonal feature decomposition and enhanced feature extraction is proposed. The effectiveness and superiority of the proposed method in predictive accuracy are demonstrated through comprehensive multi-model experiment comparisons.

Wind power forecasting using optimized LSTM by attraction–repulsion optimization algorithm

Wind power forecasting is crucial for energy conversion and management. This study employs the long short-term memory (LSTM) network, a specialized form of recurrent neural networks (RNNs) noted for its effectiveness in time-series prediction, to predict wind power from various turbines. Furthermore, we incorporate a cutting-edge metaheuristic optimization technique to optimize the training process of the LSTM, enhancing its parameter optimization. Specifically, we utilize the attraction–repulsion optimization algorithm (AROA), an innovative optimization algorithm inspired by the natural phenomena of attraction and repulsion for addressing complex optimization and engineering problems. This research applies the AROA to optimize the LSTM training process, which markedly improves the model's forecasting accuracy. Our analysis is conducted using four datasets from La Haute Borne wind turbines in France. The proposed AROA-LSTM model achieved R2 testing results of 0.9416, 0.9663, 0.9613, and 0.9622 for Turbines 1, 2, 3, and 4, respectively.

Enhancing Wind Power Forecasting Accuracy with Hybrid Deep Learning and Teaching-Learning-Based Optimization

Forecasting wind power generation is crucial for ensuring grid security and the competitiveness of the power market. This paper presents an innovative approach that combines deep learning (DL) with Teaching-Learning-Based Optimization (TLBO) to predict wind power output accurately. Using a real dataset spanning diverse weather conditions and turbine specifications collected between January 2018 and March 2020, the study employs 18 features as inputs, including Ambient Temperature, Wind Direction, and Wind Speed, with real power output in kW as the target variable. Metaheuristic algorithms including Particle Swarm Optimization (PSO), Barnacles Mating Optimizer (BMO), Biogeography-Based Optimization (BBO), and Firefly Algorithm (FA) are comprehensively compared for model optimization. TLBO-DL consistently provides forecasts that closely align with actual wind power values across instances, substantiated by its low RMSE of 98.7601, indicating effective minimization of errors in wind power forecasting. Comparative analysis with other algorithms reveals that TLBO-DL outperforms PSO-DL (RMSE: 102.6627), BMO-DL (RMSE: 132.4839), BBO-DL (RMSE: 103.8517), and FA-DL (RMSE: 104.7282) in terms of overall forecasting accuracy. The variations in the performance of other algorithms across instances highlight the robustness and effectiveness of TLBO-DL in achieving accurate wind power forecasts. Overall, TLBO-DL emerges as a reliable and superior algorithm for wind power forecasting, consistently providing accurate forecasts across a range of instances.

CrossGFA: wind power prediction with a multi-scale cross-graph network via a Frequency-Enhanced Channel attention mechanism

CrossGFA: wind power prediction with a multi-scale cross-graph network via a Frequency-Enhanced Channel attention mechanism

Real-time Error Compensation Transfer Learning with Echo State Networks for Enhanced Wind Power Prediction

Accurate wind power forecasting is essential for efficient energy management and grid stability, enabling energy providers to balance supply and demand, optimize renewable energy integration, reduce operational costs, and enhance power grid reliability. The Echo State Network (ESN) is widely used for modeling nonlinear dynamic systems due to its simple and rapid training process. However, ESNs can be prone to system errors, leading to inaccurate models when handling high-order nonlinear complexities. To overcome this, we developed the Error Compensation Transfer Learning Echo State Network (ETL-ESN), which combines a computing layer based on ESN and a compensation layer using transfer learning. Our model identifies error auto-correlation as a key factor that increases variance in ESN predictions, and addresses this with an error compensation layer to reduce system errors. We further leverage transfer learning to prevent overfitting within the error domain. Extensive experiments using real-world wind power data demonstrate that the ETL-ESN model reduces training time from 65 s to 2 s compared to LSTM, while lowering MAE by up to 95%. The ETL-ESN achieves a 95% to 98% improvement in prediction accuracy across different turbines compared to traditional models. The code and datasets used in this study are available at GitHub repository https://github.com/zhuyingqin/Error-Transfer-ESN for further research and replication.

Short-term wind power prediction based on IBOA-AdaBoost-RVM

This study introduces an innovative model, namely IBOA-AdaBoost-RVM, which leverages the Improved Butterfly Optimization Algorithm (IBOA), Adaptive Boosting (AdaBoost), and Relevance Vector Machine (RVM). This model is used to solve the problem of low precision of wind power prediction. Initially, normalization is applied to reduce the influence of varying data dimensions. Subsequently, input variables are determined through the Pearson correlation method. Lastly, the efficacy of the introduced model is assessed across four distinct seasonal monthly data sets. The observed outcomes indicate that the proposed model outperforms other models in terms of evaluation metrics, with the average R2, RMSE, MAE, and MAPE values across the four datasets being 0.954, 10.403, 7.032, and 0.645, respectively, show that the proposed method has potential in the field of wind power prediction.

IDHNet: Ultra‐Short‐Term Wind Power Forecasting With IVMD–DCInformer–HSSA Network

ABSTRACTThe variability and unpredictability of wind power generation present significant challenges for grid management and planning. Enhancing the accuracy of wind power forecasting is crucial for improving the reliability of renewable energy systems. To enhance the accuracy of temporal wind power predictions, the IVMD–DCInformer–HSSA framework has been introduced. Initially, the original wind power data is decomposed into multiple intrinsic mode function (IMF) components using the improved variational mode decomposition (IVMD) technique. Subsequently, the Sparrow search algorithm (HSSA) is employed to optimize the parameters of the enhanced Informer deep neural network, which are then integrated into the improved Informer model. The predictions of each IMF component resulting from the IVMD decomposition are then combined to generate the final prediction outcome. The experimental results show that the R‐squared value of the proposed combined model is increased to 0.9903, and the accuracy is increased by 1%–3% compared with other models, which has a good prediction effect.

Conv‐ELSTM: An ensemble deep learning approach for predicting short‐term wind power

AbstractAccurate and reliable forecasting of wind power is essential for the stable integration of wind energy into the electrical grid. However, the chaotic nature of wind power presents a significant challenge in utilizing data for effective short‐term forecasting, such as 60‐min predictions. This article introduces a hybrid data‐driven framework that employs an ensemble deep learning model to provide highly precise short‐term wind power predictions. The framework leverages a data‐driven approach to identify the intrinsic components of wind power data, including high‐frequency and low‐frequency components. A convolutional layer‐based feature fusion network is then established to properly extract important information from irrelevant wind energy features. Subsequently, an ensemble of long short‐term memory (LSTM) networks is developed to forecast wind power using the fused features, thereby mitigating the disadvantage of a single prediction model. The numerical experiment is carried out based on two different real‐life datasets. The results demonstrate the effectiveness of the proposed method in forecasting short‐term wind power compared to five benchmarks.

Wind turbine energy forecasting using real wind farm’s measurement data and performance of gene expression programming analytical model in comparison to traditional algorithms

ABSTRACT Forecasting wind power is vital to ensure steady, sustainable, and renewable energy. The complex nonlinear nature of wind flow and its interrelated factors make power prediction challenging. This study predicted wind power curves inspired by the Biologically Inspired Evolutionary Computation (BIEC) paradigm, incorporating Gene Expression Programming (GEP), Artificial Neural Networks (ANN), Least Square Support Vector Machines (LSSVM), and Random Forest (RF) models. Key input parameters include wind speed, yaw azimuth, turbulent intensity, veer, horizontal and vertical shear, ambient temperature, blade pitch, and rotor speed. The study evaluates these models’ effectiveness using root mean square error (RMSE) and correlation coefficient R. Results indicate that the GEP model offers transparent modeling, emphasizing critical inputs like wind speed, rotor speed, blade pitch angle, and temperature for wind power prediction. The GEP model identified wind speed, rotor speed, blade pitch angle, and temperature as the most influential parameters, with variable importance index (Ii) values of 69.39%, 24.39%, 5.46%, and 0.64% for training, and 69.37%, 25.03%, 4.98%, and 0.54% for validation. The study demonstrates the GEP model’s efficacy in accurately forecasting wind power curve, achieving a high correlation with training and validation coefficients of 0.9899 and 0.994, respectively, outperforming traditional models with minor errors.

The Integration of Internet of Things and Machine Learning for Energy Prediction of Wind Turbines

Wind power has emerged as a crucial substitute for conventional fossil fuels. The combination of advanced technologies such as the internet of things (IoT) and machine learning (ML) has given rise to a new generation of energy systems that are intelligent, reliable, and efficient. The wind energy sector utilizes IoT devices to gather vital data, subsequently converting them into practical insights. The aforementioned information aids among others in the enhancement of wind turbine efficiency, precise anticipation of energy production, optimization of maintenance approaches, and detection of potential risks. In this context, the main goal of this work is to combine the IoT with ML in the wind energy sector by processing weather data acquired from sensors to predict wind power generation. To this end, three different regression models are evaluated. The models under comparison include Linear Regression, Random Forest, and Lasso Regression, which were evaluated using metrics such as coefficient of determination (R²), adjusted R², mean squared error (MSE), root mean squared error (RMSE), and mean absolute error (MAE). Moreover, the Akaike Information Criterion (AIC) and Bayesian Information Criterion (BIC) were taken into consideration as well. After examining a dataset from IoT devices that included weather data, the models provided substantial insights regarding their capabilities and responses to preprocessing, as well as each model’s reaction in terms of statistical performance deviation indicators. Ultimately, the data analysis and the results from metrics and criteria show that Random Forest regression is more suitable for weather condition datasets than the other two regression models. Both the advantages and shortcomings of the three regression models indicate that their integration with IoT devices will facilitate successful energy prediction.

The short-term wind power prediction based on a multi-layer stacked model of BO[sbnd]CNN-BiGRU-SA

Wind power generation is influenced by various meteorological factors, exhibiting significant volatility and unpredictability. This variability presents considerable challenges for accurate wind power forecasting. In this study, we propose an innovative method for short-term wind power prediction that integrates a Bayesian-optimized Convolutional Neural Network (CNN), Bidirectional Gated Recurrent Units (BiGRU), and a Self-Attention Mechanism (SA) within a multi-layer architecture. Initially, we preprocess features using Pearson correlation analysis and input them into the CNN to investigate complex nonlinear spatial relationships among multiple feature variables and the current load. Subsequently, the BiGRU captures long-term dependencies from both forward and backward time sequences. Finally, we implement the Self-Attention Mechanism to weigh the features and generate the predicted wind power. We optimize the model's numerous hyperparameters utilizing a Bayesian algorithm. Through comparative ablation experiments with varying time segment lengths on wind farm datasets from four regions, our method significantly outperforms 11 models, including Long Short-Term Memory (LSTM), and surpasses several state-of-the-art (SOTA) prediction models, such as iTransformer, PatchTST, Non-stationary Transformers, TSMixer, and DLinear. The highest coefficient of determination (R²) achieved was 0.981, with the Symmetric Mean Absolute Percentage Error (SMAPE), Root Mean Square Error (RMSE), and Mean Absolute Error (MAE) decreasing by 11.22 % to 62.04 % compared to other models. The results demonstrate the predictive accuracy and generalization performance of our proposed model.

Wind and Solar Power Generation Forecasting Based on Hybrid CNN-ABiLSTM, CNN-Transformer-MLP Models

Accurate prediction of solar and wind power output is crucial for effective integration into the electrical grid. Existing methods, including conventional approaches, machine learning (ML), and hybrid models, have limitations such as limited adaptability, narrow generalizability, and difficulty in forecasting multiple types of renewable energy respectively. To address these challenges, this study introduces two novel hybrid models: the CNN-ABiLSTM, which integrates Convolutional Neural Networks (CNN) with Attention-based Bidirectional Long Short-Term Memory (ABiLSTM), and the CNN-Transformer-MLP, which integrates CNN with Transformers and Multi-Layer Perceptrons (MLP). In both hybrid models, the CNN captures short-term patterns in solar and wind power data, while the ABiLSTM and Transformer-MLP models address the long-term patterns. CNN, BiLSTM, and Encoder-based Transformer were taken as baseline standalone models. The proposed hybrid models and standalone baseline models were trained on quarter-hour-based real-time data. The hybrid models outperform standalone baseline models in day, week, and month-ahead forecasting. The CNN-Transformer-MLP hybrid provides more accurate day and week-ahead solar and wind power predictions with lower mean absolute error (MAE), root mean square error (RMSE), and mean square error (MSE) values. For month-ahead forecasts, the CNN-ABiLSTM hybrid excels in wind power prediction, demonstrating its strength in long-term forecasting.

Short-term prediction of offshore wind power based on CNN and LSTM

Abstract This paper presents an innovative short-term wind power forecasting model based on deep learning, aimed at improving the economic benefits and system stability of wind power projects. The model combines a CNN, known for efficient feature extraction, with an LSTM network, recognized for its exceptional time series processing ability. Additionally, an attention mechanism is applied to probabilistically assign weights, enhancing key feature influence and further improving wind direction prediction accuracy. First, the LSTM predicts the gas properties of the unit state, followed by a convolutional model with attention mechanisms to forecast wind power. Experimental results demonstrate that this model significantly reduces prediction errors and enhances accuracy. Specifically: 1) A comprehensive deep learning model is proposed, integrating CNN and LSTM advantages, with an attention mechanism to enhance performance. 2) Key issues in wind power forecasting are effectively addressed, improving accuracy and stability. 3) Both real and simulated data demonstrate the model’s exceptional performance. 4) Experimental results confirm that the model surpasses traditional methods with lower forecast errors and higher accuracy. Future work will focus on refining the model to handle complex environments and overcoming technical challenges in practical applications.